DKPE-GraphSYN: a drug synergy prediction model based on joint dual kernel density estimation and positional encoding for graph representation.

Introduction: Synergistic medication, a crucial therapeutic strategy in cancer treatment, involves combining multiple drugs to enhance therapeutic effectiveness and mitigate side effects. Current research predominantly employs deep learning models for extracting features from cell line and cancer drug structure data. However, these methods often overlook the intricate nonlinear relationships within the data, neglecting the distribution characteristics and weighted probability densities of gene expression data in multi-dimensional space. It also fails to fully exploit the structural information of cancer drugs and the potential interactions between drug molecules. Methods: To overcome these challenges, we introduce an innovative end-to-end learning model specifically tailored for cancer drugs, named Dual Kernel Density and Positional Encoding (DKPE) for Graph Synergy Representation Network (DKPEGraphSYN). This model is engineered to refine the prediction of drug combination synergy effects in cancer. DKPE-GraphSYN utilizes Dual Kernel Density Estimation and Positional Encoding techniques to effectively capture the weighted probability density and spatial distribution information of gene expression, while exploring the interactions and potential relationships between cancer drug molecules via a graph neural network. Results: Experimental results show that our prediction model achieves significant performance enhancements in forecasting drug synergy effects on a comprehensive cancer drug and cell line synergy dataset, achieving an AUPR of 0.969 and an AUC of 0.976. Discussion: These results confirm our model's superior accuracy in predicting cancer drug combinations, providing a supportive method for clinical medication strategy in cancer.

MFSynDCP: multi-source feature collaborative interactive learning for drug combination synergy prediction.

Drug combination therapy is generally more effective than monotherapy in the field of cancer treatment. However, screening for effective synergistic combinations from a wide range of drug combinations is particularly important given the increase in the number of available drug classes and potential drug-drug interactions. Existing methods for predicting the synergistic effects of drug combinations primarily focus on extracting structural features of drug molecules and cell lines, but neglect the interaction mechanisms between cell lines and drug combinations. Consequently, there is a deficiency in comprehensive understanding of the synergistic effects of drug combinations. To address this issue, we propose a drug combination synergy prediction model based on multi-source feature interaction learning, named MFSynDCP, aiming to predict the synergistic effects of anti-tumor drug combinations. This model includes a graph aggregation module with an adaptive attention mechanism for learning drug interactions and a multi-source feature interaction learning controller for managing information transfer between different data sources, accommodating both drug and cell line features. Comparative studies with benchmark datasets demonstrate MFSynDCP's superiority over existing methods. Additionally, its adaptive attention mechanism graph aggregation module identifies drug chemical substructures crucial to the synergy mechanism. Overall, MFSynDCP is a robust tool for predicting synergistic drug combinations. The source code is available from GitHub at https://github.com/kkioplkg/MFSynDCP .

Association between exposure to multiple metals and stress urinary incontinence in women: a mixture approach.

There is limited evidence linking exposure to heavy metals, especially mixed metals, to stress urinary incontinence (SUI). This study aimed to explore the relationship between multiple metals exposure and SUI in women. The data were derived from the National Health and Nutrition Examination Survey (NHANES), 2007-2020. In the study, a total of 13 metals were analyzed in blood and urine. In addition, 5155 adult women were included, of whom 2123 (41.2%) suffered from SUI. The logistic regression model and restricted cubic spline (RCS) were conducted to assess the association of single metal exposure with SUI risk. The Bayesian kernel machine regression (BKMR) and weighted quantile sum (WQS) were used to estimate the combined effect of multiple metals exposure on SUI. First, we observed that blood Pb, Hg and urinary Pb, Cd were positively related to SUI risk, whereas urinary W was inversely related by multivariate logistic regression (all p-FDR < 0.05). Additionally, a significant non-linear relationship between blood Hg and SUI risk was observed by RCS analysis. In the co-exposure models, WQS model showed that exposure to metal mixtures in blood [OR (95%CI) = 1.18 (1.06, 1.31)] and urine [OR (95%CI) = 1.18 (1.03, 1.34)] was positively associated with SUI risk, which was consistent with the results of BKMR model. A potential interaction was identified between Hg and Cd in urine. Hg and Cd were the main contributors to the combined effects. In summary, our study indicates that exposure to heavy metal mixtures may increase SUI risk in women.

Photochromism and single-component white light emission from a metalloviologen complex based on 1,5-naphthyridine.

Metalloviologens, as emerging electron-transfer photochromic compounds, have shown intriguing properties such as radiochromism, photochromism and photoconductance. However, only a limited number of them have been reported so far. Exploration of new metalloviologens is strongly desired. Herein, we report a new solvothermally synthesized metalloviologen complex [CdCl2(ND)2]n (1, ND = 1,5-naphthalenes) that exhibits photochromic and intrinsic white light emission properties. Density functional theory calculation results reveal that the photochromism could be assigned to photoinduced electron transfer from chlorine atoms to ND molecules. The photoinduced charge-separated states are heat/air stable, attributed to the delocalization of ND and strong intermolecular π-π interactions. Besides, complex 1 consistently emits intrinsic white light when excited with 340-370 nm UV light, achieving high color rendering index (CRI) values (82.54-94.04). By adjusting the excitation wavelength, both "warm" and "cold" white light emission can be produced, making it suitable for the application of a white light emitting diode (WLED). Thus, this work demonstrates that the ND-based metalloviologen is not only helpful in producing photochromism, but also beneficial for creating white-light emission.

SM-GRSNet: sparse mapping-based graph representation segmentation network for honeycomb lung lesion.

Objective. Honeycomb lung is a rare but severe disease characterized by honeycomb-like imaging features and distinct radiological characteristics. Therefore, this study aims to develop a deep-learning model capable of segmenting honeycomb lung lesions from Computed Tomography (CT) scans to address the efficacy issue of honeycomb lung segmentation.Methods. This study proposes a sparse mapping-based graph representation segmentation network (SM-GRSNet). SM-GRSNet integrates an attention affinity mechanism to effectively filter redundant features at a coarse-grained region level. The attention encoder generated by this mechanism specifically focuses on the lesion area. Additionally, we introduce a graph representation module based on sparse links in SM-GRSNet. Subsequently, graph representation operations are performed on the sparse graph, yielding detailed lesion segmentation results. Finally, we construct a pyramid-structured cascaded decoder in SM-GRSNet, which combines features from the sparse link-based graph representation modules and attention encoders to generate the final segmentation mask.Results. Experimental results demonstrate that the proposed SM-GRSNet achieves state-of-the-art performance on a dataset comprising 7170 honeycomb lung CT images. Our model attains the highest IOU (87.62%), Dice(93.41%). Furthermore, our model also achieves the lowest HD95 (6.95) and ASD (2.47).Significance.The SM-GRSNet method proposed in this paper can be used for automatic segmentation of honeycomb lung CT images, which enhances the segmentation performance of Honeycomb lung lesions under small sample datasets. It will help doctors with early screening, accurate diagnosis, and customized treatment. This method maintains a high correlation and consistency between the automatic segmentation results and the expert manual segmentation results. Accurate automatic segmentation of the honeycomb lung lesion area is clinically important.

Preparation of CuO@humic acid@carbon nanotube composite material using humic acid as a coupling agent and its lithium-ion storage performance.

The conventional Li-ion battery composite electrode material composed of CuO and carbon nanotubes (CNTs) suffer from poor contact between CuO and CNTs. This results in high electrode resistance and poor electrochemical performance. To solve this problem, CuO@humic acid (HA) @CNT anode material with cross-linked network structure was generated by linking CuO and CNT with HA as a coupling agent. For comparison, CuO@HA or CuO@CNT were also prepared in the absence of CNT or HA, respectively. The results showed that CuO@HA@CNT had lower charge transfer resistance, higher conductivity, lithium-ion diffusion coefficient, specific capacity, and rate capability than CuO@HA and CuO@CNT. The specific capacity of the CuO@HA@CNT electrode was significantly better than that of the composite electrode materials of CuO and CNT, which have been prepared by scientists using various methods. Due to the introduction of HA, not only was the uniformly distributed flower-like CuO obtained, but also the specific capacity and rate capability of the electrode material were substantially improved. This study thus provides a good strategy to optimize the capability of transition metal oxide lithium-ion anode materials.

Efficient photocatalytic hydrogen evolution: Linkage units engineering in triazine-based conjugated porous polymers.

Conjugated porous polymers (CPPs) have been widely reported as promising photocatalysts. However, the realization of powerful photocatalytic hydrogen production performance still benefits from the rational design of molecular frameworks and the appropriate choice of building monomers. Herein, we synthesized two novel conjugated porous polymers (CPPs) by copolymerizing pyrene and 1,3,5-triazine building blocks. It is found that minor structural changes in the peripheral groups of the triazine units can greatly affect the photocatalytic activity of the polymers. Compared with the phenyl-linkage unit, the thiophene-linkage unit can give CPP a wider absorption range of visible light, a narrower band gap, a higher transmission and separation efficiency of photo-generated carriers (electrons/holes), and a better interface contact with the photocatalytic reaction solution. The catalyst containing thiophene-triazine (ThPy-CPP) has an efficient photocatalytic hydrogen evolution rate of 21.65 and 16.69 mmol g-1h-1 under full-arc spectrum and visible light without the addition of a Pt co-catalyst, respectively, much better than the one containing phenyl-triazine (PhPy-CPP, only 5.73 and 3.48 mmol g-1h-1). This study provides a promising direction to design and construct highly efficient, cost-effective CPP-based photocatalysts, for exploring the application of noble metal-free catalysts in photocatalytic hydrogen evolution.

Enhanced photocatalytic hydrogen evolution activity of co-catalyst free S-scheme polymer heterojunctions via ultrasonic assisted reorganization in solvent.

In this work, two donor-acceptor linear conjugated polymers were designed and synthesized based on thianthrene-5,5,10,10-tetraoxide (TTO) as the acceptor unit, benzo[1,2-b:4,5-b']dithiophene derivative (Py1) and thiophene (Py2) as the donor units, respectively. The Py1/Py2 composite was prepared by physical ball milling of the two polymers in a mixture, which was further treated with a N-methyl-2-pyrrolidone (NMP)-assisted sonication treatment, and the obtained catalyst was named N-Py1/Py2. Compared with the single polymer or Py1/Py2, the FTIR characteristic peaks of O=S=O have a red shift for N-Py1/Py2, accompanied by a profound change in morphology. Furthermore, N-Py1/Py2 has a broader light response and more efficient separation and transport of charge carriers, and as a result it exhibits a higher photocatalytic hydrogen evolution rate (26.5 mmol g-1 h-1) without the involvement of any co-catalyst than Py1/Py2 catalyst (3.56 mmol g-1 h-1). The underlying mechanism for the enhanced photocatalytic activity by the sonication treatment in NMP is discussed based both on experimental and theoretical calculation data.

Pt Nanoparticles Confined in a 3D Porous FeNC Matrix as Efficient Catalysts for Rechargeable Li-CO2/O2 Batteries.

The cathodic product Li2CO3, due to its high decomposition potential, has hindered the practical application of rechargeable Li-CO2/O2 batteries. To overcome this bottleneck, a Pt/FeNC cathodic catalyst is fabricated by dispersing Pt nanoparticles (NPs) with a uniform size of 2.4 nm and 8.3 wt % loading amount into a porous microcube FeNC support for high-performance rechargeable Li-CO2/O2 batteries. The FeNC matrix is composed of numerous two-dimensional (2D) carbon nanosheets, which is derived from an Fe-doping zinc metal-organic framework (Zn-MOF). Importantly, using Pt/FeNC as the cathodic catalyst, the Li-CO2/O2 (VCO2/VO2 = 4:1) battery displays the lowest overpotential of 0.54 V and a long-term stability of 142 cycles, which is superior to batteries with FeNC (1.67 V, 47 cycles) and NC (1.87 V, 23 cycles) catalysts. The FeNC matrix and Pt NPs can exert a synergetic effect to decrease the decomposition potential of Li2CO3 and thus enhance the battery performance. In situ Fourier transform infrared (FTIR) spectroscopy further confirms that Li2CO3 can be completely decomposed under a low potential of 3.3 V using the Pt/FeNC catalyst. Impressively, Li2CO3 exhibits a film structure on the surface of the Pt/FeNC catalysts by scanning electron microscopy (SEM), and its size can be limited by the confined space between the carbon sheets in Pt/FeNC, which enlarges the better contacting interface. In addition, density functional theory (DFT) calculations reveal that the Pt and FeNC catalysts show a higher adsorption energy for Li2CO3 and Li2CO4 intermediates compared to the NC catalyst, and the possible discharge pathways are deeply investigated. The synergetic effect between the FeNC support and Pt active sites makes the Li-CO2/O2 battery achieve optimal performance.

Gm-PLoc: A Subcellular Localization Model of Multi-Label Protein Based on GAN and DeepFM.

Identifying the subcellular localization of a given protein is an essential part of biological and medical research, since the protein must be localized in the correct organelle to ensure physiological function. Conventional biological experiments for protein subcellular localization have some limitations, such as high cost and low efficiency, thus massive computational methods are proposed to solve these problems. However, some of these methods need to be improved further for protein subcellular localization with class imbalance problem. We propose a new model, generating minority samples for protein subcellular localization (Gm-PLoc), to predict the subcellular localization of multi-label proteins. This model includes three steps: using the position specific scoring matrix to extract distinguishable features of proteins; synthesizing samples of the minority category to balance the distribution of categories based on the revised generative adversarial networks; training a classifier with the rebalanced dataset to predict the subcellular localization of multi-label proteins. One benchmark dataset is selected to evaluate the performance of the presented model, and the experimental results demonstrate that Gm-PLoc performs well for the multi-label protein subcellular localization.

Anchoring NiO Nanosheet on the Surface of CNT to Enhance the Performance of a Li-O2 Battery.

Li2O2, as the cathodic discharge product of aprotic Li-O2 batteries, is difficult to electrochemically decompose. Transition-metal oxides (TMOs) have been proven to play a critical role in promoting the formation and decomposition of Li2O2. Herein, a NiO/CNT catalyst was prepared by anchoring a NiO nanosheet on the surface of CNT. When using the NiO/CNT as a cathode catalyst, the Li-O2 battery had a lower overpotential of 1.2 V and could operate 81 cycles with a limited specific capacity of 1000 mA h g-1 at a current density of 100 mA g-1. In comparison, with CNT as a cathodic catalyst, the battery could achieve an overpotential of 1.64 V and a cycling stability of 66 cycles. The introduction of NiO effectively accelerated the generation and decomposition rate of Li2O2, further improving the battery performance. SEM and XRD characterizations confirmed that a Li2O2 film formed during the discharge process and could be fully electrochemical decomposed in the charge process. The internal network and nanoporous structure of the NiO/CNT catalyst could provide more oxygen diffusion channels and accelerate the decomposition rate of Li2O2. These merits led to the Li-O2 battery's better performance.

A Novel Remote Sensing Image Registration Algorithm Based on Feature Using ProbNet-RANSAC.

Image registration based on feature is a commonly used approach due to its robustness in complex geometric deformation and larger gray difference. However, in practical application, due to the effect of various noises, occlusions, shadows, gray differences, and even changes of image contents, the corresponding feature point set may be contaminated, which may degrade the accuracy of the transformation model estimate based on Random Sample Consensus (RANSAC). In this work, we proposed a semi-automated method to create the image registration training data, which greatly reduced the workload of labeling and made it possible to train a deep neural network. In addition, for the model estimation based on RANSAC, we determined the process according to a probabilistic perspective and presented a formulation of RANSAC with the learned guidance of hypothesis sampling. At the same time, a deep convolutional neural network of ProbNet was built to generate a sampling probability of corresponding feature points, which were then used to guide the sampling of a minimum set of RANSAC to acquire a more accurate estimation model. To illustrate the effectiveness and advantages of the proposed method, qualitative and quantitative experiments are conducted. In the qualitative experiment, the effectiveness of the proposed method was illustrated by a checkerboard visualization of image pairs before and after being registered by the proposed method. In the quantitative experiment, other three representative and popular methods of vanilla RANSAC, LMeds-RANSAC, and ProSAC-RANSAC were compared, and seven different measures were introduced to comprehensively evaluate the performance of the proposed method. The quantitative experimental result showed that the proposed method had better performance than the other methods. Furthermore, with the integration of the model estimation of the image registration into the deep-learning framework, it was possible to jointly optimize all the processes of image registration via end-to-end learning to further improve the accuracy of image registration.

Accuracy of conventional ultrasound, contrast-enhanced ultrasound and dynamic contrast-enhanced magnetic resonance imaging in assessing the size of breast cancer.

OBJECTIVE: This study was performed to investigate the accuracy of conventional ultrasound (US), contrast-enhanced US (CEUS), and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in assessing the size of breast cancer. METHODS: In total, 49 breast cancer lesions of 48 patients were included in this study. The inclusion criteria were the performance of total mastectomy or breast-conserving surgery for treatment of breast cancer in our hospital from January 2017 to December 2020 with complete pathological results, as well as the performance of conventional US, CEUS, and DCE-MRI examinations with complete results. The exclusion criteria were non-mass breast cancer shown on conventional US or DCE-MRI, including that found on CEUS with no boundary with surrounding tissues and no confirmed tumor scope; a tumor too large to be completely displayed in the US section, thus affecting the measurement results; the presence of two nodules in the same breast that were too close to each other to be distinguished by any of the three imaging methods; and treatment with preoperative chemotherapy. Preoperative conventional US, CEUS, and DCE-MRI examinations were performed. The postoperative pathological results were taken as the gold standard. The lesion size was represented by its maximum diameter. The accuracy, overestimation, and underestimation rates of conventional US, CEUS, and DCE-MRI were compared. RESULTS: The maximum lesion diameter on US, CEUS, DCE-MRI and pathology were 1.62±0.63 cm (range, 0.6-3.5 cm), 2.05±0.75 cm (range, 1.0-4.0 cm), 1.99±0.74 cm (range, 0.7-4.2 cm) and 1.92±0.83 cm (range, 0.5-4.0 cm), respectively. The lesion size on US was significantly smaller than that of postoperative pathological tissue (P < 0.05). However, there was no significant difference between the CEUS or DCE-MRI results and the pathological results. The underestimation rate of conventional US (55.1%, 27/49) was significantly higher than that of CEUS (20.4%, 10/49) and DCE-MRI (24.5%, 12/49) (P < 0.001 and P = 0.002, respectively). There was no significant difference in the accuracy of CEUS (36.7%, 18/49) and DCE-MRI (34.7%, 17/49) compared with conventional US (26.5%, 13/49); however, the accuracy of both groups tended to be higher than that of conventional US. The overestimation rate of CEUS (42.9%, 21/49) and DCE-MRI (40.8%, 20/49) was significantly higher than that of conventional US (18.4%, 9/49) (P = 0.001 and P = 0.015, respectively). CONCLUSIONS: CEUS and DCE-MRI show similar performance when evaluating the size of breast cancer. However, CEUS is more convenient, has a shorter operation time, and has fewer restrictions on its use. Notably, conventional US is more prone to underestimate the size of lesions, whereas CEUS and DCE-MRI are more prone to overestimate the size.

Triazine-Based Conjugated Microporous Polymers With Different Linkage Units for Visible Light-Driven Hydrogen Evolution.

Conjugated microporous polymers (CMPs), as a kind of two-dimensional material, have attracted extensive attention due to their advantages in visible light-driven photocatalytic splitting of water for hydrogen evolution. However, improving the microstructure and electronic structure of the material to enhance their photocatalytic performance for hydrogen evolution remains a challenge. We designed and reported two analogous CMPs including CMP-1 and CMP-2 that contain triazine and dibenzothiophene-S,S-dioxide units, which were prepared by Pd-catalyzed Suzuki-Miyaura coupling reaction. The main difference of two CMPs is that the triazine units are connected to benzene unit (CMP-1) or thiophene unit (CMP-2). Both of the CMPs exhibit excellent light capture capability, and compared with CMP-2, CMP-1 has faster separation rates and lower recombination rates for the charge carriers (electron/hole), and then, a higher hydrogen evolution rate was obtained from water decomposition reaction. We find the H2 production rate of CMP-1 can be up to 9,698.53 µmol g-1h -1, which is about twice of that of CMP-2. This work suggests that molecular design is a potent method to optimize the photocatalytic performance toward hydrogen evolution of the CMPs.

Unraveling the Interfacial Polarization Effect between Pd and Polymeric Carbon Nitride toward Efficient CO2 Electroreduction to CO.

The efficient electrochemical conversion of carbon dioxide (CO2) to carbon monoxide (CO) using renewable energy is an effective route to pursue carbon neutrality. Optimizing the binding energy of CO on palladium (Pd) metal-based materials used in this process is to make sure the timely desorption of CO from their active sites is critical. Tuning the electronic structure of the Pd center is an effective strategy to optimize its catalytic performance. Herein, we rationally design Pd nanoparticles (NPs)/polymeric carbon nitride (CN) (Pd/CN) composite, which alters the electronic structure of Pd by introducing the interfacial polarization effect to accelerate CO desorption and improve CO selectivity of Pd catalyst. The optimized Pd/CN exhibits a CO Faradaic efficiency of 92.7% at -0.9 V versus reversible hydrogen electrode in CO2-saturated 0.1 M KHCO3 solution. Experimental investigations and theoretical calculations jointly confirm that the enhanced CO selectivity and stability originate from the electron transfer at the Pd/CN interface, and the weakened *CO adsorption on the palladium hydride surface.

Low-dose computed tomography image reconstruction via a multistage convolutional neural network with autoencoder perceptual loss network.

Background: Computed tomography (CT) is widely used in medical diagnoses due to its ability to non-invasively detect the internal structures of the human body. However, CT scans with normal radiation doses can cause irreversible damage to patients. The radiation exposure is reduced with low-dose CT (LDCT), although considerable speckle noise and streak artifacts in CT images and even structural deformation may result, significantly undermining its diagnostic capability. Methods: This paper proposes a multistage network framework which gradually divides the entire process into 2-staged sub-networks to complete the task of image reconstruction. Specifically, a dilated residual convolutional neural network (DRCNN) was used to denoise the LDCT image. Then, the learned context information was combined with the channel attention subnet, which retains local information, to preserve the structural details and features of the image and textural information. To obtain recognizable characteristic details, we introduced a novel self-calibration module (SCM) between the 2 stages to reweight the local features, which realizes the complementation of information at different stages while refining feature information. In addition, we also designed an autoencoder neural network, using a self-supervised learning scheme to train a perceptual loss neural network specifically for CT images. Results: We evaluated the diagnostic quality of the results and performed ablation experiments on the loss function and network structure modules to verify each module's effectiveness in the network. Our proposed network architecture obtained high peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and visual information fidelity (VIF) values in terms of quantitative evaluation. In the analysis of qualitative results, our network structure maintained a better balance between eliminating image noise and preserving image details. Experimental results showed that our proposed network structure obtained better metrics and visual evaluation. Conclusions: This study proposed a new LDCT image reconstruction method by combining autoencoder perceptual loss networks with multistage convolutional neural networks (MSCNN). Experimental results showed that the newly proposed method has performance than other methods.

COVID-19 CT image recognition algorithm based on transformer and CNN.

Novel corona virus pneumonia (COVID-19) broke out in 2019, which had a great impact on the development of world economy and people's lives. As a new mainstream image processing method, deep learning network has been constructed to extract medical features from chest CT images, and has been used as a new detection method in clinical practice. However, due to the medical characteristics of COVID-19 CT images, the lesions are widely distributed and have many local features. Therefore, it is difficult to diagnose directly by using the existing deep learning model. According to the medical features of CT images in COVID-19, a parallel bi-branch model (Trans-CNN Net) based on Transformer module and Convolutional Neural Network module is proposed by making full use of the local feature extraction capability of Convolutional Neural Network and the global feature extraction advantage of Transformer. According to the principle of cross-fusion, a bi-directional feature fusion structure is designed, in which features extracted from two branches are fused bi-directionally, and the parallel structures of branches are fused by a feature fusion module, forming a model that can extract features of different scales. To verify the effect of network classification, the classification accuracy on COVIDx-CT dataset is 96.7%, which is obviously higher than that of typical CNN network (ResNet-152) (95.2%) and Transformer network (Deit-B) (75.8%). These results demonstrate accuracy is improved. This model also provides a new method for the diagnosis of COVID-19, and through the combination of deep learning and medical imaging, it promotes the development of real-time diagnosis of lung diseases caused by COVID-19 infection, which is helpful for reliable and rapid diagnosis, thus saving precious lives.

Feasibility and efficiency of contrast enhanced ultrasound real time guided fine needle aspiration for sentinel lymph node of breast cancer.

AIM: To assess the feasibility and efficiency of contrast-enhanced ultrasound (CEUS) real-time guided fine needle aspiration (FNA) for sentinel lymph node (SLN) of breast cancer. MATERIALS AND METHODS: This retrospective study reviewed 21 breast cancer patients who scheduled for surgical resection performed CEUS real-time guided SLN-FNA and intraoperative SLN biopsy (SLNB). The success rate of CEUS real-time guided SLN-FNA was analyzed. The FNA diagnostic efficiency of SLN metastasis was analyzed compared to SLNB. RESULTS: Twenty-six SLNs were detected by intradermal CEUS whereas 130 SLNs were detected by SLNB. The median SLNs detected by intradermal CEUS (n = 1) and by SLNB (n = 5) was significantly difference (p < 0.001). All 26 CE-SLNs of 21 patients were successfully performed intradermal CEUS dual image real-time guided SLN-FNA including 5 SLNs of 4 patients which were difficult to distinguish in conventional ultrasound. Compared to SLNB, FNA found 2 of 5 cases of SLN metastasis, the diagnosis sensitivity, specificity, positive predictive value, negative predictive value, false negative rate, false positive rate and Yoden index were 40%, 100%, 100%, 84.2%, 60%, 0%and 40%, respectively. CONCLUSION: SLN-FNA real-time guided by dual CEUS image mode was technically feasible. Patients with a positive SLN-FNA should be advised to ALND without intraoperative SLNB according to Chinese surgeon and patients' conservatism attitude. But a negative SLN-FNA did not obviate the need of conventional SLNB because of the high false negative rate.

Exploration of the prognostic signature reflecting tumor microenvironment of lung adenocarcinoma based on immunologically relevant genes.

Lung adenocarcinoma (LUAD) represents the major histological type of lung cancer with high mortality globally. Due to the heterogeneous nature, the same treatment strategy to various patients may result in different therapeutic responses. Hence, we aimed to elaborate an effective signature for predicting patient survival outcomes. The TCGA-LUAD cohort from the TCGA portal was used as a training dataset. The GSE26939 and GSE68465 cohorts from the GEO database were taken as validation datasets. All immunologically relevant genes were extracted from the ImmPort. The ESTIMATE algorithm was employed to explore LUAD microenvironment in the training dataset. Further, the DEGs were picked out based on the immune-associated genes reflecting different statuses in the immune context of TME. Univariate/multivariate Cox regression was performed to determine six prognosis- specific genes (PIK3CG, BTK, VEGFD, INHA, INSL4, and PTPRC) and established a risk predictive signature. The time-dependent ROC indicated that AUC values were all greater than 0.70 at 1-, 3-, and 5- year intervals. Corresponding RiskScore of each LUAD patient was calculated from the signature, and they were stratified into the high- and low-risk groups by the median value of RiskScore. K-M curves and Log-rank test demonstrated significant survival differences between the two groups (P < 0.05). Similar results were exhibited in the validation datasets. The RiskScore was incredibly relevant to clinicopathological factors like gender, AJCC stage, and T stage. Also, it can mirror the distribution state of 15 kinds of TIICs and have some predictive value for the sensitivity of therapeutic drugs.

Multi-channel multi-task deep learning for predicting EGFR and KRAS mutations of non-small cell lung cancer on CT images.

BACKGROUND: Predicting the mutation statuses of 2 essential pathogenic genes [epidermal growth factor receptor (EGFR) and Kirsten rat sarcoma (KRAS)] in non-small cell lung cancer (NSCLC) based on CT is valuable for targeted therapy because it is a non-invasive and less costly method. Although deep learning technology has realized substantial computer vision achievements, CT imaging being used to predict gene mutations remains challenging due to small dataset limitations. METHODS: We propose a multi-channel and multi-task deep learning (MMDL) model for the simultaneous prediction of EGFR and KRAS mutation statuses based on CT images. First, we decomposed each 3D lung nodule into 9 views. Then, we used the pre-trained inception-attention-resnet model for each view to learn the features of the nodules. By combining 9 inception-attention-resnet models to predict the types of gene mutations in lung nodules, the models were adaptively weighted, and the proposed MMDL model could be trained end-to-end. The MMDL model utilized multiple channels to characterize the nodule more comprehensively and integrate patient personal information into our learning process. RESULTS: We trained the proposed MMDL model using a dataset of 363 patients collected by our partner hospital and conducted a multi-center validation on 162 patients in The Cancer Imaging Archive (TCIA) public dataset. The accuracies for the prediction of EGFR and KRAS mutations were, respectively, 79.43% and 72.25% in the training dataset and 75.06% and 69.64% in the validation dataset. CONCLUSIONS: The experimental results demonstrated that the proposed MMDL model outperformed the latest methods in predicting EGFR and KRAS mutations in NSCLC.